Loading...
Paper Number
1470
Paper Type
short
Description
This study analyzed the admission outcomes in chronic patients (with COPD, and Liver disease) to demonstrate the feasibility of applying prediction methods on EHR records while incorporating an explainable AI technique. We predicted three target variables: 30-day readmission, Medium&Long Length of Stay and Single-day admission and analyzed the features using an explainable AI technique, the SHapley Additive exPlanations (SHAP). The results show that Readmission had higher prediction scores than all other dependent variables. Some features affected all target variables with either positive or negative influence including: Age, Charlson comorbidity index, Day-Shift, Gender, using EHR screens and Insurance cover level. These findings thus point to the value of using Machine-Learning combined with an explainable AI method to understand and assess the risks factors. The assessment of the potential factors leading to multiple complications can bolster prevention-oriented medical decisions to groups of patients but can also be tailored to the patient level.
Recommended Citation
Ben-Assuli, Ofir and Geva, Gaya, "Analyzing Patients’ EHR: Predicting and Explaining Admission Consequences for COPD and Liver Disease Patients" (2023). ICIS 2023 Proceedings. 6.
https://aisel.aisnet.org/icis2023/ishealthcare/ishealthcare/6
Analyzing Patients’ EHR: Predicting and Explaining Admission Consequences for COPD and Liver Disease Patients
This study analyzed the admission outcomes in chronic patients (with COPD, and Liver disease) to demonstrate the feasibility of applying prediction methods on EHR records while incorporating an explainable AI technique. We predicted three target variables: 30-day readmission, Medium&Long Length of Stay and Single-day admission and analyzed the features using an explainable AI technique, the SHapley Additive exPlanations (SHAP). The results show that Readmission had higher prediction scores than all other dependent variables. Some features affected all target variables with either positive or negative influence including: Age, Charlson comorbidity index, Day-Shift, Gender, using EHR screens and Insurance cover level. These findings thus point to the value of using Machine-Learning combined with an explainable AI method to understand and assess the risks factors. The assessment of the potential factors leading to multiple complications can bolster prevention-oriented medical decisions to groups of patients but can also be tailored to the patient level.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
16-HealthCare